{"total":92,"rows":[{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019,"area":null},{"id":"2303.17564","title":"BloombergGPT: A Large Language Model for Finance","created":"2023-03-30","cited_by_count":939,"area":null},{"id":"2403.07815","title":"Chronos: Learning the Language of Time Series","created":"2024-03-12","cited_by_count":759,"area":null},{"id":"2311.16867","title":"The Falcon Series of Open Language Models","created":"2023-11-28","cited_by_count":535,"area":null},{"id":"2305.16264","title":"Scaling Data-Constrained Language Models","created":"2023-05-25","cited_by_count":403,"area":null},{"id":"2205.05131","title":"UL2: Unifying Language Learning Paradigms","created":"2022-05-10","cited_by_count":295,"area":null},{"id":"2307.10169","title":"Challenges and Applications of Large Language Models","created":"2023-07-19","cited_by_count":254,"area":null},{"id":"2202.06991","title":"Transformer Memory as a Differentiable Search Index","created":"2022-02-14","cited_by_count":247,"area":null},{"id":"2408.12569","title":"Sapiens: Foundation for Human Vision Models","created":"2024-08-22","cited_by_count":229,"area":null},{"id":"2304.05969","title":"Localizing Model Behavior with Path Patching","created":"2023-04-12","cited_by_count":195,"area":null},{"id":"2405.18392","title":"Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations","created":"2024-05-28","cited_by_count":170,"area":null},{"id":"2111.10952","title":"ExT5: Towards Extreme Multi-Task Scaling for Transfer Learning","created":"2021-11-22","cited_by_count":161,"area":null},{"id":"2403.08540","title":"Language models scale reliably with over-training and on downstream tasks","created":"2024-03-13","cited_by_count":113,"area":null},{"id":"2110.02095","title":"Exploring the Limits of Large Scale Pre-training","created":"2021-10-05","cited_by_count":104,"area":null},{"id":"2207.10551","title":"Scaling Laws vs Model Architectures: How does Inductive Bias Influence Scaling?","created":"2022-07-21","cited_by_count":103,"area":null},{"id":"2110.12894","title":"The Efficiency Misnomer","created":"2021-10-25","cited_by_count":98,"area":null},{"id":"2210.15424","title":"What Language Model to Train if You Have One Million GPU Hours?","created":"2022-10-27","cited_by_count":92,"area":null},{"id":"2303.11504","title":"Language Model Behavior: A Comprehensive Survey","created":"2023-03-20","cited_by_count":92,"area":null},{"id":"2305.13035","title":"Getting ViT in Shape: Scaling Laws for Compute-Optimal Model Design","created":"2023-05-22","cited_by_count":89,"area":null},{"id":"2406.19146","title":"Resolving Discrepancies in Compute-Optimal Scaling of Language Models","created":"2024-06-27","cited_by_count":88,"area":null},{"id":"2210.14199","title":"Same Pre-training Loss, Better Downstream: Implicit Bias Matters for Language Models","created":"2022-10-25","cited_by_count":84,"area":null},{"id":"2212.09803","title":"Training Trajectories of Language Models Across Scales","created":"2022-12-19","cited_by_count":81,"area":null},{"id":"2503.13423","title":"SuperBPE: Space Travel for Language Models","created":"2025-03-17","cited_by_count":63,"area":null},{"id":"2506.06105","title":"Text-to-LoRA: Instant Transformer Adaption","created":"2025-06-06","cited_by_count":58,"area":null},{"id":"2110.11403","title":"SCENIC: A JAX Library for Computer Vision Research and Beyond","created":"2021-10-18","cited_by_count":57,"area":null},{"id":"2210.11399","title":"Transcending Scaling Laws with 0.1% Extra Compute","created":"2022-10-20","cited_by_count":57,"area":null},{"id":"2312.10523","title":"Paloma: A Benchmark for Evaluating Language Model Fit","created":"2023-12-16","cited_by_count":54,"area":null},{"id":"2205.12253","title":"Evaluating the Impact of Model Scale for Compositional Generalization in Semantic Parsing","created":"2022-05-24","cited_by_count":50,"area":null},{"id":"2410.08527","title":"Scaling Laws for Predicting Downstream Performance in LLMs","created":"2024-10-11","cited_by_count":48,"area":null},{"id":"2310.19956","title":"The Impact of Depth on Compositional Generalization in Transformer Language Models","created":"2023-10-30","cited_by_count":38,"area":null},{"id":"2111.04130","title":"NLP From Scratch Without Large-Scale Pretraining: A Simple and Efficient Framework","created":"2021-11-07","cited_by_count":34,"area":null},{"id":"2402.02314","title":"Selecting Large Language Model to Fine-tune via Rectified Scaling Law","created":"2024-02-04","cited_by_count":33,"area":null},{"id":"2502.12170","title":"MUDDFormer: Breaking Residual Bottlenecks in Transformers via Multiway Dynamic Dense Connections","created":"2025-02-13","cited_by_count":31,"area":null},{"id":"2506.11300","title":"Beyond Random Sampling: Efficient Language Model Pretraining via Curriculum Learning","created":"2025-06-12","cited_by_count":26,"area":null},{"id":"2202.06387","title":"Scaling Laws Under the Microscope: Predicting Transformer Performance from Small Scale Experiments","created":"2022-02-13","cited_by_count":23,"area":null},{"id":"2405.01964","title":"Position: Understanding LLMs Requires More Than Statistical Generalization","created":"2024-05-03","cited_by_count":21,"area":null},{"id":"2203.03759","title":"IT5: Text-to-text Pretraining for Italian Language Understanding and Generation","created":"2022-03-07","cited_by_count":20,"area":null},{"id":"2308.07120","title":"Position: Key Claims in LLM Research Have a Long Tail of Footnotes","created":"2023-08-14","cited_by_count":20,"area":null},{"id":"2110.08467","title":"Improving Compositional Generalization with Self-Training for Data-to-Text Generation","created":"2021-10-16","cited_by_count":19,"area":null},{"id":"2211.03796","title":"Astronomia ex machina: a history, primer, and outlook on neural networks in astronomy","created":"2022-11-07","cited_by_count":17,"area":null},{"id":"2410.03464","title":"S7: Selective and Simplified State Space Layers for Sequence Modeling","created":"2024-10-04","cited_by_count":17,"area":null},{"id":"2501.18107","title":"Scaling Inference-Efficient Language Models","created":"2025-01-30","cited_by_count":16,"area":null},{"id":"2510.05197","title":"Efficient Prediction of Pass@k Scaling in Large Language Models","created":"2025-10-06","cited_by_count":16,"area":null},{"id":"2203.02094","title":"LiteTransformerSearch: Training-free Neural Architecture Search for Efficient Language Models","created":"2022-03-04","cited_by_count":14,"area":null},{"id":"2505.03793","title":"LENSLLM: Unveiling Fine-Tuning Dynamics for LLM Selection","created":"2025-05-01","cited_by_count":14,"area":null},{"id":"2401.14373","title":"TURNA: A Turkish Encoder-Decoder Language Model for Enhanced Understanding and Generation","created":"2024-01-25","cited_by_count":13,"area":null},{"id":"2411.02142","title":"Training Compute-Optimal Protein Language Models","created":"2024-11-04","cited_by_count":12,"area":null},{"id":"2302.06117","title":"The Framework Tax: Disparities Between Inference Efficiency in NLP Research and Deployment","created":"2023-02-13","cited_by_count":11,"area":null},{"id":"2412.00631","title":"ROSE: A Reward-Oriented Data Selection Framework for LLM Task-Specific Instruction Tuning","created":"2024-12-01","cited_by_count":10,"area":null},{"id":"2502.06244","title":"PiKE: Adaptive Data Mixing for Large-Scale Multi-Task Learning Under Low Gradient Conflicts","created":"2025-02-10","cited_by_count":8,"area":null},{"id":"2507.06445","title":"Can Interpretation Predict Behavior on Unseen Data?","created":"2025-07-08","cited_by_count":8,"area":null},{"id":"2205.11833","title":"Diverse Lottery Tickets Boost Ensemble from a Single Pretrained Model","created":"2022-05-24","cited_by_count":7,"area":null},{"id":"2310.10054","title":"NASH: A Simple Unified Framework of Structured Pruning for Accelerating Encoder-Decoder Language Models","created":"2023-10-16","cited_by_count":7,"area":null},{"id":"2508.15390","title":"Exploiting Vocabulary Frequency Imbalance in Language Model Pre-training","created":"2025-08-21","cited_by_count":7,"area":null},{"id":"2311.04666","title":"Pre-training LLMs using human-like development data corpus","created":"2023-11-08","cited_by_count":5,"area":null},{"id":"2409.05780","title":"Breaking Neural Network Scaling Laws with Modularity","created":"2024-09-09","cited_by_count":5,"area":null},{"id":"2409.13530","title":"Towards Long-Context Time Series Foundation Models","created":"2024-09-20","cited_by_count":5,"area":null},{"id":"2205.10505","title":"A Study on Transformer Configuration and Training Objective","created":"2022-05-21","cited_by_count":4,"area":null},{"id":"2310.15129","title":"Location-Aware Visual Question Generation with Lightweight Models","created":"2023-10-23","cited_by_count":4,"area":null},{"id":"2409.05782","title":"Unified Neural Network Scaling Laws and Scale-time Equivalence","created":"2024-09-09","cited_by_count":4,"area":null},{"id":"2503.04302","title":"Malware Detection at the Edge with Lightweight LLMs: A Performance Evaluation","created":"2025-03-06","cited_by_count":4,"area":null},{"id":"2506.11389","title":"Curriculum-Guided Layer Scaling for Language Model Pretraining","created":"2025-06-13","cited_by_count":4,"area":null},{"id":"2510.18245","title":"Scaling Laws Meet Model Architecture: Toward Inference-Efficient LLMs","created":"2025-10-21","cited_by_count":4,"area":null},{"id":"2301.10444","title":"An Experimental Study on Pretraining Transformers from Scratch for IR","created":"2023-01-25","cited_by_count":3,"area":null},{"id":"2504.13219","title":"Scaling Laws for Data-Efficient Visual Transfer Learning","created":"2025-04-17","cited_by_count":3,"area":null},{"id":"2604.02320","title":"Large-scale Codec Avatars: The Unreasonable Effectiveness of Large-scale Avatar Pretraining","created":"2026-04-02","cited_by_count":3,"area":null},{"id":"2505.15252","title":"An Efficient Private GPT Never Autoregressively Decodes","created":"2025-05-21","cited_by_count":2,"area":null},{"id":"2506.21570","title":"Random Initialization Can't Catch Up: The Advantage of Language Model Transfer for Time Series Forecasting","created":"2025-06-12","cited_by_count":2,"area":null},{"id":"2508.17400","title":"Retrieval Capabilities of Large Language Models Scale with Pretraining FLOPs","created":"2025-08-24","cited_by_count":2,"area":null},{"id":"2509.23963","title":"Evaluating the Robustness of Chinchilla Compute-Optimal Scaling","created":"2025-09-28","cited_by_count":2,"area":null},{"id":"2601.20994","title":"The Depth Delusion: Why Transformers Should Be Wider, Not Deeper","created":"2026-01-28","cited_by_count":2,"area":null},{"id":"2609.19107","title":"How Model Growth, Recursion, and Boundary Operators Influence Scaling Exponents","created":"2026-09-16","cited_by_count":2,"area":null},{"id":"2210.12410","title":"The Shared Task on Gender Rewriting","created":"2022-10-22","cited_by_count":1,"area":null},{"id":"2302.09150","title":"Cluster-Guided Label Generation in Extreme Multi-Label Classification","created":"2023-02-17","cited_by_count":1,"area":null},{"id":"2304.02721","title":"To Asymmetry and Beyond: Structured Pruning of Sequence to Sequence Models for Improved Inference Efficiency","created":"2023-04-05","cited_by_count":1,"area":null},{"id":"2505.19990","title":"Progressive Scaling Visual Object Tracking","created":"2025-05-26","cited_by_count":1,"area":null},{"id":"2606.18246","title":"Variable-Width Transformers","created":"2026-06-16","cited_by_count":1,"area":null},{"id":"2609.32534","title":"DepthBench: Measuring How Residual Connections Enable More Computational Depth","created":"2026-09-26","cited_by_count":1,"area":null},{"id":"2310.02044","title":"How Physics and Background Attributes Impact Video Transformers in Robotic Manipulation: A Case Study on Planar Pushing","created":"2023-10-03","cited_by_count":0,"area":null},{"id":"2311.04166","title":"Perturbed examples reveal invariances shared by language models","created":"2023-11-07","cited_by_count":0,"area":null},{"id":"2311.15964","title":"Efficient Pre-training for Localized Instruction Generation of Videos","created":"2023-11-27","cited_by_count":0,"area":null},{"id":"2312.14504","title":"Theory of Hallucinations based on Equivariance","created":"2023-12-22","cited_by_count":0,"area":null},{"id":"2401.14421","title":"Multi-Agent Based Transfer Learning for Data-Driven Air Traffic Applications","created":"2024-01-23","cited_by_count":0,"area":null},{"id":"2509.12267","title":"A Traditional Approach to Symbolic Piano Continuation","created":"2025-09-13","cited_by_count":0,"area":null},{"id":"2510.14614","title":"First Attentions Last: Better Exploiting First Attentions for Efficient Transformer Training","created":"2025-10-16","cited_by_count":0,"area":null},{"id":"2511.12188","title":"Scaling Law Analysis in Federated Learning: How to Select the Optimal Model Size?","created":"2025-11-15","cited_by_count":0,"area":null},{"id":"2511.14111","title":"CascadedViT: Cascaded Chunk-FeedForward and Cascaded Group Attention Vision Transformer","created":"2025-11-18","cited_by_count":0,"area":null},{"id":"2512.07522","title":"LIME: Making LLM Data More Efficient with Linguistic Metadata Embeddings","created":"2025-12-08","cited_by_count":0,"area":null},{"id":"2603.04478","title":"Standing on the Shoulders of Giants: Rethinking EEG Foundation Model Pretraining via Multi-Teacher Distillation","created":"2026-03-04","cited_by_count":0,"area":null},{"id":"2606.00284","title":"Specializing Without Forgetting: Analyzing Knowledge Preservation in Multilingual Model Adaptation","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2607.09885","title":"Index SLM Technical Report","created":"2026-07-10","cited_by_count":0,"area":null},{"id":"2610.08183","title":"Compact Robot Policies Need Fine-Grained Visual Representations","created":"2026-10-06","cited_by_count":0,"area":null}],"next_cursor":null}